Journal
COMPUTERS AND ELECTRONICS IN AGRICULTURE
Volume 193, Issue -, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.compag.2021.106675
Keywords
Face recognition; RetinaFace; ArcFace loss; Deep learning; Precision livestock
Funding
- China Scholarship Council, China [202003250122]
- Inner Mongolia Autonomous Region Science and Technology Major Project, China [2020ZD0004]
- National Natural Science Foundation of China, China [32060776]
- Hebei Province Key Research and Development Plan, China [20327202D, 19220119D]
- Youth Science Foundation of Jiangxi Province, China [20192ACBL21023]
- Doctoral program of innovation fund of Jiangxi Academy of Agricultural Sciences, China [20181CBS006]
Ask authors/readers for more resources
In this study, a novel cattle identification framework named CattleFaceNet was proposed, which integrated RetinaFace-mobilenet for face detection and location, and ArcFace for improving the within-class compactness and between-class discrepancy during training. The experimental results showed that CattleFaceNet outperformed other methods in terms of identification accuracy and processing time, demonstrating its potential for real-time livestock identification in practical production scenarios.
Cattle identification is crucial to be registered for breeding association, food quality tracing, disease prevention and control and fake insurance claims. Traditional non-biometrics methods for cattle identification is not really satisfactory in providing reliability due to theft, fraud, and duplication. In this study, a computer vision technique was proposed to facilitate precision animal management and improve livestock welfare. This paper presents a novel face identification framework by integrating light-weight RetinaFace-mobilenet with Additive Angular Margin Loss (ArcFace), namely CattleFaceNet. RetinaFace-mobilenet is designed for face detection and location, and ArcFace is adopted to strengthen the within-class compactness and also between-class discrepancy during training. Experiments on real-word scenarios dataset prove that RetinaFace-mobilenet achieves superior detection performance and significantly accelerates the computation time against RetinaNet. Three loss functions utilized in human face recognition combined with RetinaFace-mobilenet are compared and results indict that the proposed CattleFaceNet outperforms others with identification accuracy of 91.3% and processing time of 24 frames per second (FPS). This research work demonstrates the potential candidate of CattleFaceNet for livestock identification in real time in practical production scenarios.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available